INDEX

Explanations

Random text 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

tm

-0.27

å¨ģå°Ķ

-0.26

 discipl

-0.26

 [][]

-0.25

é¢ĦåĪ¶

-0.24

çħĬ

-0.24

Williams

-0.24

æĤ¬

-0.23

ä¿®å£«

-0.23

[][

-0.23

POSITIVE LOGITS

 rush

0.28

IPH

0.26

 dash

0.26

dash

0.25

/provider

0.25

 purposely

0.24

III

0.24

rne

0.24

 frenzy

0.24

çĪ·

0.23

Activations Density 0.005%

Random text snippets

No Comments

No Known Activations