INDEX

Explanations

allergic reactions

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

çĤķ

-0.27

bik

-0.26

äºı

-0.26

cycle

-0.26

ycle

-0.26

 cycle

-0.25

åĪ¤

-0.25

è¹ĩ

-0.25

virtual

-0.24

 virtual

-0.24

POSITIVE LOGITS

itus

0.27

è¿¸

0.26

çĽ´è¾¾

0.26

 tslib

0.25

åĬ¨äºº

0.25

ToJson

0.25

\web

0.25

é¢Ħè§ģ

0.25

éº»

0.25

 foresee

0.25

Activations Density 0.006%

allergic reactions

No Comments

No Known Activations