INDEX

Explanations

software/web service logs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¯Ĩ

-0.31

allas

-0.28

çĻ¾åº¦

-0.28

PER

-0.27

ieres

-0.26

ç¦º

-0.25

|--

-0.25

ledge

-0.25

 ----------------------------------------------------------------------------------------------------------------

-0.24

 McMaster

-0.24

POSITIVE LOGITS

reuse

0.26

Bow

0.25

 famously

0.25

QA

0.25

æ¦´

0.25

ENA

0.24

GameData

0.24

deserialize

0.24

getCell

0.24

mux

0.23

Activations Density 0.034%

software/web service logs

No Comments

No Known Activations