INDEX

Explanations

ic

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç²¾åįİ

-0.31

Balancer

-0.28

TK

-0.27

 Tess

-0.27

æ°ĳ

-0.26

 hung

-0.26

æĲħ

-0.26

çľŁè¯ļ

-0.26

nika

-0.25

è¯·åģĩ

-0.25

POSITIVE LOGITS

anske

0.27

onnen

0.26

{_

0.25

åĽŀäºĭ

0.25

olon

0.25

(ctrl

0.24

{|

0.24

ä¹ĭä¹¡

0.24

 Baton

0.24

 affirmative

0.24

Activations Density 0.037%

ic

No Comments

No Known Activations