INDEX

Explanations

code snippets

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

 purpose

-0.27

 outs

-0.26

 hinter

-0.25

 meetup

-0.25

anst

-0.25

/not

-0.25

stead

-0.24

ushman

-0.24

/access

-0.24

sted

-0.24

POSITIVE LOGITS

åįģæĿ¡

0.33

åĽĽçº§

0.26

åįģä¸ª

0.26

 averages

0.25

erb

0.25

ç»Ŀå¯¹

0.25

å¹³åĿĩ

0.24

_SZ

0.24

aju

0.24

(Sql

0.24

Activations Density 0.178%

code snippets

No Comments

No Known Activations