INDEX

Explanations

major

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 awakening

-0.31

isci

-0.28

æ¶¨ä»·

-0.27

awning

-0.26

ÑģÑĤÐ°Ð²ÐºÐ°

-0.26

 custody

-0.26

Ø³Ùĥ

-0.26

Own

-0.25

ility

-0.25

 Government

-0.25

POSITIVE LOGITS

passes

0.29

 Explorer

0.28

 explorer

0.27

 probing

0.27

å¤§åŃ¦æ¯ķä¸ļ

0.27

æĤį

0.26

TURE

0.25

Ð»Ð°Ñģ

0.25

kok

0.24

occus

0.24

Activations Density 0.003%

major

No Comments

No Known Activations