INDEX

Explanations

have

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

cks

-0.26

è´Łè½½

-0.25

fixtures

-0.25

oids

-0.25

 áº¤

-0.23

scoped

-0.23

/^\

-0.23

[[]

-0.23

Dup

-0.23

DisplayStyle

-0.23

POSITIVE LOGITS

é¦

0.28

å¹Ķ

0.28

 rehabilit

0.27

éľĢè¦ģçĶ¨åĪ°

0.25

ilib

0.25

ä¸Ģä½ĵ

0.25

éĥ½éľĢè¦ģ

0.25

çıĪ

0.24

inker

0.24

å¿ĥæĦı

0.24

Activations Density 0.020%

have

No Comments

No Known Activations