INDEX

Explanations

code, legal, academic text

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

 scientific

-0.34

ç§ĳçłĶ

-0.28

ç§ĳåŃ¦çłĶç©¶

-0.28

 Institutes

-0.28

è¯ļ

-0.27

scient

-0.27

 institutes

-0.26

çłĶç©¶äººåĳĺ

-0.26

ç§ĳ

-0.26

ammers

-0.25

POSITIVE LOGITS

 appellate

0.32

 chiáº¿u

0.28

dda

0.27

 graduation

0.26

æį»

0.25

åĴ«

0.25

ç°½

0.25

.setResult

0.24

çŃ¾

0.24

 hang

0.24

Activations Density 0.002%

code, legal, academic text

No Comments

No Known Activations