INDEX

Explanations

research and studies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eway

-0.28

 injuring

-0.27

ä¼°è®¡

-0.27

 /*#__

-0.27

)['

-0.27

çĽ¾

-0.26

ä¸Ńæ¯Ĵ

-0.26

 parch

-0.25

damage

-0.25

 hurting

-0.25

POSITIVE LOGITS

ÑĤÐµÐ»ÑĮÐ½Ð¾

0.28

 afforded

0.27

adors

0.27

à¸ªà¸§

0.26

urses

0.26

ady

0.26

ierge

0.25

 afford

0.24

å¹Į

0.24

_LD

0.24

Activations Density 0.059%

research and studies

No Comments

No Known Activations