INDEX

Explanations

forward slash

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

_mut

-0.29

å¤§åıĶ

-0.27

 butt

-0.26

 qualitative

-0.26

 qual

-0.25

 contests

-0.25

{}.

-0.25

quals

-0.25

aud

-0.24

mis

-0.24

POSITIVE LOGITS

ãĢħ

0.28

äººäºº

0.26

 clipped

0.26

ellular

0.26

èĮ¬

0.25

ä»£è¨Ģ

0.25

æĪį

0.25

åħ³

0.24

 extremes

0.24

 earliest

0.24

Activations Density 0.004%

forward slash

No Comments

No Known Activations