INDEX

Explanations

steam

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 ErrorHandler

-0.25

 heirs

-0.25

aket

-0.24

Patterns

-0.24

 underestimated

-0.24

äº²è¿ĳ

-0.24

åĪ°æĹ¶åĢĻ

-0.24

ä»ĸå·²ç»ı

-0.24

 Ultr

-0.23

dol

-0.23

POSITIVE LOGITS

less

0.30

-faced

0.29

-fr

0.28

 crews

0.27

/fr

0.27

 sparing

0.26

æ£Ĵ

0.26

obar

0.25

 hotter

0.25

çļĦæĦıä¹ī

0.25

Activations Density 0.034%

steam

No Comments

No Known Activations