INDEX

Explanations

later

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

ç¬ĥ

-0.32

å¾Ĺå¾Ī

-0.31

çļĦç¨ĭåº¦

-0.28

lul

-0.27

eur

-0.26

ionate

-0.25

ä¸įä½İäºİ

-0.25

_weather

-0.24

pol

-0.24

é£İæļ´

-0.24

POSITIVE LOGITS

 deter

0.27

ases

0.25

Hay

0.25

ieres

0.25

æľīæľºä¼ļ

0.25

 presses

0.25

Hay

0.25

edic

0.24

hay

0.24

å®ļä½į

0.24

Activations Density 0.056%

later

No Comments

No Known Activations