INDEX

Explanations

scientific research papers

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

è¿ĻäºĽéĹ®é¢ĺ

-0.31

 Roch

-0.28

å¾Ĺèµ·

-0.26

åłª

-0.26

 distribution

-0.25

 arrangements

-0.25

distribution

-0.25

 placement

-0.25

 distribute

-0.24

ikes

-0.24

POSITIVE LOGITS

erez

0.32

æ¾

0.27

weed

0.27

æİ¥åĬĽ

0.27

hunter

0.26

mother

0.26

gad

0.26

ç¸½

0.25

 Widow

0.25

:System

0.25

Activations Density 0.265%

scientific research papers

No Comments

No Known Activations