INDEX

Explanations

active/activated

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Scholar

-0.26

solution

-0.26

sim

-0.26

æļĳ

-0.25

pic

-0.25

sur

-0.25

éģĬãģ³

-0.25

Ä±ÅŁÄ±

-0.24

 spot

-0.24

 bottom

-0.23

POSITIVE LOGITS

.fi

0.31

 sacked

0.29

brtc

0.25

Append

0.24

sock

0.24

 clubhouse

0.24

RuleContext

0.24

 dicts

0.23

(reader

0.23

 Silence

0.23

Activations Density 0.004%

active/activated

No Known Activations