INDEX

Explanations

technical/patent text

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

($__

-0.27

ç³»

-0.27

des

-0.27

 attach

-0.27

des

-0.26

 straps

-0.26

rig

-0.26

 attached

-0.25

ly

-0.25

isten

-0.25

POSITIVE LOGITS

á»¥c

0.30

ilarity

0.28

 Agents

0.27

stamp

0.26

-highlight

0.26

ÏĬ

0.25

å®ł

0.25

 Gloss

0.24

åľ°éģĵ

0.24

Ã§e

0.24

Activations Density 0.067%

technical/patent text

No Comments

No Known Activations