INDEX

Explanations

a

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

æĸ¹éĿ¢

-0.28

ç©ºæ°Ķä¸Ń

-0.26

_via

-0.25

ries

-0.25

è¯ķåīĤ

-0.25

ç¥ŀèī²

-0.25

 airs

-0.24

orners

-0.24

Characters

-0.24

rys

-0.24

POSITIVE LOGITS

astic

0.29

Suppress

0.28

 Bracket

0.25

æľŁå¾ħ

0.25

ç«Ļ

0.24

æĪĳä»¬å°Ĩ

0.24

shall

0.24

HasKey

0.24

çĽĳçĿ£

0.24

 compared

0.24

Activations Density 0.001%

a

No Comments

No Known Activations