INDEX

Explanations

Text excerpts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Dual

-0.30

 dual

-0.30

gage

-0.26

_dual

-0.25

 immunity

-0.25

:UI

-0.25

imer

-0.25

 Dual

-0.25

getline

-0.24

ãģĹãģªãģĮãĤī

-0.24

POSITIVE LOGITS

ä¹ĭæĺŁ

0.29

ì§ĳ

0.26

esis

0.25

 stemming

0.24

é¦Ĵ

0.24

 putt

0.24

 renegot

0.24

_party

0.24

ossa

0.23

 tráº¡ng

0.23

Activations Density 0.245%

Text excerpts

No Comments

No Known Activations