INDEX

Explanations

ally

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ä»

-0.28

å¤§æĸ¹

-0.26

ä¹Ĺ

-0.26

å¿Ĵ

-0.25

 Boys

-0.25

atel

-0.24

 gá»įn

-0.24

å¯¡

-0.24

lic

-0.24

Updates

-0.24

POSITIVE LOGITS

 setC

0.27

åĪº

0.25

(arguments

0.25

 pixels

0.25

 genus

0.25

pixels

0.25

ÑĥÐ»

0.25

åľ¨åħ¶

0.24

run

0.24

åī¡

0.24

Activations Density 0.000%

ally

No Comments

No Known Activations