INDEX

Explanations

command line, programming

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

 housing

-0.27

Documentation

-0.27

ä½ıæĪ¿

-0.26

ä½ıæĪ¿åĴĮ

-0.26

ä½İæ¸©

-0.26

å¾Īä½İ

-0.26

å®Īä½ı

-0.25

housing

-0.25

ington

-0.25

boro

-0.24

POSITIVE LOGITS

çĮ·

0.27

æºĨ

0.26

 Paren

0.26

retch

0.25

OrUpdate

0.25

quina

0.25

pname

0.25

kaz

0.25

kla

0.24

 Saudis

0.24

Activations Density 0.070%

command line, programming

No Comments

No Known Activations