INDEX

Explanations

Mixed languages and code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hand

-0.31

 stab

-0.31

 shot

-0.30

-hand

-0.30

åĪĴ

-0.29

_handlers

-0.27

èĤĥ

-0.27

 Hand

-0.27

 MyApp

-0.26

hardt

-0.26

POSITIVE LOGITS

æĺ¯çľŁçļĦ

0.27

 testim

0.27

 einz

0.26

ames

0.26

ewis

0.25

Thing

0.25

culate

0.25

æĿ±è¥¿

0.25

."),

0.25

ÂŃtion

0.24

Activations Density 0.001%

Mixed languages and code

No Comments

No Known Activations