INDEX

Explanations

Code/Technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

urnished

-0.28

ÑĤÐ°ÑĢ

-0.27

_setopt

-0.26

 Ø§ÙĦØªØ§Ø¨

-0.26

æ³

-0.26

è¿Ļä¸ªåľ°åĽ¾

-0.25

ç§¯ç´¯äºĨ

-0.25

å½Ĺ

-0.25

CodeAt

-0.25

-boot

-0.24

POSITIVE LOGITS

cer

0.28

 Anthrop

0.27

Ã´

0.27

amines

0.26

YSIS

0.26

amine

0.25

 performances

0.25

.br

0.25

Ã©rio

0.24

æĻĤéĸĵãĤĴ

0.24

Activations Density 0.067%

Code/Technical writing

No Comments

No Known Activations