INDEX

Explanations

code/technical snippets

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

è¡ĢèĦī

-0.32

Smith

-0.27

éĺŁ

-0.26

gettext

-0.25

Î²

-0.25

smooth

-0.25

 kitty

-0.25

 auprÃ¨s

-0.25

ieux

-0.25

aby

-0.25

POSITIVE LOGITS

ether

0.26

OS

0.26

Ã´te

0.26

graduate

0.25

ensor

0.25

osate

0.25

onis

0.24

 Private

0.24

ape

0.24

Opp

0.24

Activations Density 0.000%

code/technical snippets

No Comments

No Known Activations