INDEX

Explanations

Cancer/channel abbreviations

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

-agent

-0.28

ä¸ºæŃ¤

-0.27

æ³¨

-0.26

ideo

-0.26

 agent

-0.25

è§Ĥä¼Ĺ

-0.25

-def

-0.25

-t

-0.25

idor

-0.24

æ¯ıæ¯ı

-0.24

POSITIVE LOGITS

_subject

0.30

onders

0.29

 Subject

0.29

onas

0.28

 Useful

0.27

Subject

0.27

ç¾İæĦŁ

0.26

subject

0.26

ocl

0.26

subj

0.26

Activations Density 0.008%

Cancer/channel abbreviations

No Comments

No Known Activations